Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2726 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9456. Min Range: -4.9456
Max Act: 4.9456. Min Act: -0.1700
Data Index: 92038 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9456. Min Range: -4.9456
Max Act: 4.8519. Min Act: -0.1700
Data Index: 2677151 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9456. Min Range: -4.9456
Max Act: 4.8206. Min Act: -0.1700
Data Index: 6029408 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9456. Min Range: -4.9456
Max Act: 4.8206. Min Act: -0.1700
Data Index: 7360339 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9456. Min Range: -4.9456
Max Act: 4.7581. Min Act: -0.1700
Data Index: 5452694 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9456. Min Range: -4.9456
Max Act: 4.7269. Min Act: -0.1700
Data Index: 3470351 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9456. Min Range: -4.9456
Max Act: 4.7269. Min Act: -0.1700
Data Index: 7045626 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9456. Min Range: -4.9456
Max Act: 4.6956. Min Act: -0.1700
Data Index: 8557209 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9456. Min Range: -4.9456
Max Act: 4.6956. Min Act: -0.1700
Data Index: 1423973 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9456. Min Range: -4.9456
Max Act: 4.6644. Min Act: -0.1700
Data Index: 4899878 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9456. Min Range: -4.9456
Max Act: 4.6331. Min Act: -0.1700
Data Index: 241655 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9456. Min Range: -4.9456
Max Act: 4.6019. Min Act: -0.1700
Data Index: 7563316 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9456. Min Range: -4.9456
Max Act: 4.6331. Min Act: -0.1700
Data Index: 467745 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9456. Min Range: -4.9456
Max Act: 4.6331. Min Act: -0.1700
Data Index: 5238952 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9456. Min Range: -4.9456
Max Act: 4.5706. Min Act: -0.1700
Data Index: 2304209 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9456. Min Range: -4.9456
Max Act: 4.6019. Min Act: -0.1700
Data Index: 312207 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9456. Min Range: -4.9456
Max Act: 4.6019. Min Act: -0.1700
Data Index: 4650473 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9456. Min Range: -4.9456
Max Act: 4.6019. Min Act: -0.1700
Data Index: 7944680 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9456. Min Range: -4.9456
Max Act: 4.6019. Min Act: -0.1700
Data Index: 8093693 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9456. Min Range: -4.9456
Max Act: 4.6019. Min Act: -0.1700
Data Index: 1258908 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #19